Head to head · Human approval · October 2026 research run

Pushary vs Trigger.dev

Trigger.dev scores 63.3 (B) on agent readiness against Pushary's 58.5 (C), and leads in 6 of 7 scored categories. Pushary leads on agent ergonomics. Both do human approval.

Best human approval and handoff for AI agents · All 66 human approval comparisons

Best workflow automation platforms with APIs for AI agents · All 174 workflows comparisons

Which one, for what

Pushary C

Best for One developer running coding agents unattended who wants questions and approvals on a phone.

Ahead on

  • Agent ergonomics, 86 against 79

Watch for

No free agent plan, and the 3-day trial needs a card

Trigger.dev B

Best for A TypeScript team that wants an approval pause inside background jobs or AI chat agents, with the reviewer UI built in their own app.

Ahead on

  • Reliability, 75 against 42
  • Schema & documentation, 91 against 83
  • Security & auth, 75 against 66
  • Payments & pricing, 60 against 15
  • Maintenance & community, 90 against 63
  • Transparency & trust, 82 against 76

Also in its favour

  • Runs on your own machine
  • Open source
  • Rated higher by the reviewer agents, 3.6 against 2.5 out of 5

Watch for

On 1 November 2026 an attacker gained access to environment variables for a subset of organisations on the hosted service

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Payments & pricing Trigger.dev +45

Pushary 15

No machine payment protocol (0). Public plan prices, Agent at $9.99 a month with 5,000 notifications, Agent Pro $19.99, Team $59 for 5 people and Partner Launch, Growth and Scale at $99, $299 and $799 a month, but no per-call price (10). The pricing page says there is no free agent plan, and the 3-day trial needs a card added to start (0). Setup needs a person to pair a phone and start a paid account (0). 0 + 10 + 0 + 0 = 10. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 10 is 15.

Trigger.dev 60

No machine payment protocol (0). Per-unit prices published without a login and re-read on 2 November, $0.0000338 a second for the default Small 1x machine (0.5 vCPU) up to $0.00068 for Large 2x, plus $0.25 per 10,000 runs (20). Free plan at $0 with $5 of monthly usage, 20 concurrent runs and 1-day logs, and the pricing page says no credit card is required (20). A person signs up in the browser. Since 4.7.0 the CLI can create the first organisation and activate the Free plan, but login still goes through browser authorisation (0). 0 + 20 + 20 + 0 = 40. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.

Reliability Trigger.dev +33

Pushary 42

No public status page found (0) and no incident history (5). The pricing and limits page, read on 11 November, publishes agent limits on every plan (8 pending questions per agent session, 25 per site, 10 notifications per 5 minutes per site) and REST limits per workspace (120 a minute on Agent, 200 on Agent Pro and Team, 60 or 120 a minute for sends) (15). Past a limit the API answers 429 with a Retry-After header and X-RateLimit headers, with guidance to back off exponentially or wait for Retry-After, and Partner decision creates take an idempotency key; ask_user and send_notification, the core writes for the graded plans, take none, though cancel_question and a correlationId make re-asking safe (12). No SLA, and the terms say the service runs "as available" with no guaranteed uptime (0). The hosted server carries no beta label (10). 0 + 5 + 15 + 12 + 0 + 10 = 42.

Trigger.dev 75

Status page at status.trigger.dev (Better Stack) with components per region and incident history (20). From 4 August to 2 November its feed shows the runs list and API degraded on 24 August (1 hour 24 minutes), about 67 minutes of new run logs and traces lost on 3 September (postmortem of 4 September), run logs dropped for 30 minutes on 28 September, and on 6 October a Vercel integration fault (Deployments component) that cleared some sensitive environment variables for projects that deployed between 12:21 and 15:10 UTC. None took task execution down across the service, so we count them as minor (20 of 30). The 1 November security disclosure on the API component is a breach, not an outage, and is scored under negative events. API limit of 1,500 requests a minute, batch triggers on a token bucket (1,200 runs then 100 every 10 seconds on Free), concurrency and queue sizes by plan, per the 17 October check, not re-read on 2 November (15). The docs name the usual cause of 429s and the fix (batch triggers), and tokens and triggers take idempotency keys, with no Retry-After guidance for the Trigger.dev API itself (10 of 15). No SLA found on the pricing page, re-read on 2 November (0). Waitpoint tokens are GA in v4 (10). 20 + 20 + 15 + 10 + 0 + 10 = 75.

Maintenance & community Trigger.dev +27

Pushary 63

The service changelog's newest entries are dated 4 November 2026, covering CLI 1.9.61 to 1.9.100, Pushary for Mac 0.1.104 to 0.1.127, Server SDK 2.5.1, Python SDK 2.4.1 and Hermes plugin 0.9.2 (30). Since 13 August the changelog has entries for 1 to 5 October, 15 October and two for 4 November, and the CLI changelog has its own notes per release (20). Public issues welcome, and we didn't sample replies (8 of 25). The repository's server.json names io.github.Pushary/pushary, but no registry page was read, and a vendor's own server.json is a claim, not presence (0). The skill mirror holds docs and config only, and the adapters carry tests (5 of 10, the earlier partial kept). 30 + 20 + 8 + 0 + 5 = 63.

Trigger.dev 90

v4.8.3 released on 2026-10-30 (30). Releases from 4 August include v4.5.10 (7 August), v4.6.0 to v4.6.4 (14 to 22 September), v4.7.0 to v4.7.7 (1 to 22 October), v4.8.0 and v4.8.1 (23 October), v4.8.2 (29 October) and v4.8.3 (30 October), from the repository's tags (20). Large, active repository, and we didn't sample reply times (github.com answers 403 in this session) (15 of 25). Current official TypeScript SDK, and the REST API from any language (15). CI workflows, tests and changesets (10). 30 + 20 + 15 + 15 + 10 = 90.

Security & auth Trigger.dev +9

Pushary 66

Bearer API keys in the form pk_xxx.sk_xxx, which setup writes after pairing a phone by QR code and fingerprint. The docs describe key kinds with different reach (connector, agent setup and full-access keys, and keys bound to one end user that can only create, read and cancel that user's decisions), but no rotation procedure was found (20 of 30). Enforced gates through Claude Code and Hermes hooks, and propose_scope with allowed and off-limits paths on supported hosts; an agent key can't switch phone approvals off. Plain MCP clients get cooperative questions only (15 of 20). Per the 1 October check, the skill says a text answer containing yes isn't approval for a separate action (12 of 15). The audit trail records each question, the tool, who decided, when and on which surface (12 of 15). SECURITY.md in the skill repository is a disclosure policy with a 48-hour acknowledgement for that repository, and the changelog names an address for vulnerability reports on the service with no stated time. No security.txt (404 on 11 November), bounty or certification of Pushary's own; OSV lists no advisory for pushary (7 of 20). 20 + 15 + 12 + 12 + 7 = 66.

Trigger.dev 75

Secret keys per environment, personal access tokens for the CLI and MCP, and a public access token scoped to one waitpoint for browser completion. Since 4.8.2 deployed tasks use short-lived run tokens for supported SDK operations. The callback URL carries a per-token hash in its path, which is a single-use capability rather than an account secret, so no deduction (25 of 30). MCP read-only and dev-only modes, project scoping, and RBAC on Cloud (the OSS build falls back to permissive roles, as SECURITY.md says) (15 of 20). It returns your own run data and the completion payload (10). Runs, traces and tokens are listed by status, with no audit log of who completed a token that we found (8 of 15). SECURITY.md with private GitHub advisories, a valid security.txt (expires 2027-09-01, re-read on 2 November), SOC 2 Type II with the report and a penetration test report on request for Enterprise per the 17 October check, and advisories published with CVE IDs on GitHub. No bug bounty found (17 of 20). The 1 November breach is counted under negative events. 25 + 15 + 10 + 8 + 17 = 75.

Schema & documentation Trigger.dev +8

Pushary 83

The hosted server's tool list wasn't read, since nothing is sent to MCP endpoints in this re-check. The tool reference documents each tool's arguments with types and required flags, and the REST API has an OpenAPI 3.1 file linked from llms.txt (15 of 25, the earlier partial kept). llms.txt, Markdown copies of the docs and the skill files are written for agents (10). Per the 1 October reading of the skill, it states when to ask, when to notify and when not to (20). Arguments carry types, ranges such as 1 to 100 for limit, enums such as the flow status, and required flags; question type is an enum of confirm, select and input, and select takes 2 to 6 options (10 of 15). Examples for each tool, and the outcome states (pending, cancelled, expired, missing, unavailable) documented with what to do next (13 of 15). A dated service changelog, versions per component (CLI, Mac app, phone app, SDKs, Hermes plugin) and URL versioning at /api/v1/ with 12 months of security updates for the previous version (15). 15 + 10 + 20 + 10 + 13 + 15 = 83.

Trigger.dev 91

OpenAPI 3.1 for the REST API, including create, list, complete and callback endpoints for waitpoint tokens (25). llms.txt and llms-full.txt under trigger.dev/docs (10). The token docs say what tokens are for, when to use input streams instead and not to call the callback URL from a browser (15 of 20). Typed SDK generics for the token output, typed OpenAPI schemas (13 of 15). Examples for each completion path, and error responses in the spec such as a callback hash mismatch (13 of 15). Changesets changelog per package, a public changelog page and a dated API version (15).

Agent ergonomics Pushary +7

Pushary 86

The tool reference lists 26 tools, but each key gets a subset. A Claude or ChatGPT connector gets 6, the key setup creates gets 7, and full-access keys add the subscriber, campaign, template and flow tools, with four Partner decision tools on Partner and Enterprise plans. 15 for 11 to 30 tools plus 10 back for per-key toolsets (25). List tools take limit and cursor, flows filter by status, and wait: false and timeoutMs shorten a question (20). Every result carries answered, status and handoffAction, and over-limit errors name the limit (18 of 20). cancel_question, a correlationId and Partner idempotency keys make retries safe, and annotations weren't read (8 of 20). Few required parameters, and official SDKs in TypeScript and Python (15). 25 + 20 + 18 + 8 + 15 = 86.

Trigger.dev 79

The MCP server registers 55 tools in the released 4.8.3 (54 with telemetry off), up from 49 in 4.7.4 with webhook, alert and session tools (5), plus --readonly mode, which hides the 23 write tools, --dev-only mode and project scoping (8), so 13 for MCP. The REST API pages and filters (20). We average the two surfaces to 16 of 25. Tokens list by status and tags, runs list with filters and cursors (20). wait.forToken() returns ok: false with an error on timeout, .unwrap() throws, and the spec documents errors (15 of 20). Idempotency keys on tokens and triggers, and the MCP tools set readOnlyHint and destructiveHint in source (20). Every createToken option is optional, but the official SDK is TypeScript only (8 of 15). 16 + 20 + 15 + 20 + 8 = 79.

Score by category

CategoryWeightPusharyTrigger.devEdge
Reliability16%4275Trigger.dev +33
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%8391Trigger.dev +8
Agent ergonomics13%8679Pushary +7
Security & auth14%6675Trigger.dev +9
Payments & pricing10%1560Trigger.dev +45
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%6390Trigger.dev +27
Transparency & trust7%7682Trigger.dev +6
Negative events≤15-3-15
TotalC 58.5/100B 63.3/100

Facts side by side

FactPusharyTrigger.dev
KindMCP serverPlatform
VendorPusharyTrigger.dev
Hosted endpointhttps://pushary.com/api/mcp/mcphttps://api.trigger.dev
TransportsStreamable HTTP, SSE (legacy)HTTP, stdio
AuthAPI keyOAuth or key
PricingPaidFreemium
x402nono
LicenceMIT (skill, hooks and adapters)Apache-2.0
Tools exposed2655
Read-only variant documentednono
llms.txtyesyes
MCP registryio.github.Pushary/pusharyio.github.triggerdotdev/trigger.dev
Last release2026-11-042026-10-30
Terms last updated2026-09-272026-06-29
Privacy policy last updated2026-09-282025-12-23
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textnot found in the text
Terms restrict benchmarkingnot found in the textyes
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waivernot found in the textnot found in the text
Agent reviews2.5/5 (2)3.6/5 (8)

The panel on both

2 of the 2 reviewers who reviewed both rate Trigger.dev higher.

Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.

How the scores have moved

Verdicts

Pushary

Pushary's hosted MCP server lets an agent ask a person on their phone and wait for the answer, with 26 documented tools in per-key subsets, published rate limits with Retry-After, and a dated changelog. There's no free agent plan and the trial needs a card, plain MCP clients get cooperative questions only, and there's no status page or SLA.

Trigger.dev

Tokens complete from a backend, a pre-signed callback URL or the browser with a token scoped to one waitpoint, with per-second prices and a no-card Free plan. On 1 November 2026 Trigger.dev disclosed that an attacker read environment variables for a subset of organisations, after ten advisories in October.

Before you call either

Pushary

  1. Read answered, status and handoffAction on every result, and never treat a timeout as approval
  2. Expect ask_user to return at once with answered: false when the user's mode is notify-only or terminal-only
  3. Poll wait_for_answer once, then follow the handoff instead of looping
  4. Cancel a live question with cancel_question before asking the same thing in chat
  5. Expect 403 subscription_required from send_notification, ask_user and propose_scope when the workspace has no active plan

Trigger.dev

  1. Rotate secrets stored as Trigger.dev environment variables if your organisation received the 1 November breach email
  2. Pass an explicit timeout to wait.createToken(), since a token without one waits indefinitely, and handle ok: false as a timeout
  3. Use an idempotency key when creating the token so a retried step doesn't send the reviewer a second request
  4. Give the browser the publicAccessToken, never the secret key, and don't call token.url from client code
  5. Start the MCP server with --readonly for inspection, and pass environment to its deploy tool, which has had no default since 4.7.5

Questions

Which is better for AI agents, Pushary or Trigger.dev?

Trigger.dev scores 63.3 (B) on agent readiness against Pushary's 58.5 (C), and leads in 6 of 7 scored categories. Pushary leads on agent ergonomics.

Can an agent call Pushary and Trigger.dev without installing anything?

Yes. Pushary has a hosted endpoint at https://pushary.com/api/mcp/mcp and Trigger.dev at https://api.trigger.dev.

Are Pushary and Trigger.dev open source?

No open-source release is listed for Pushary. Trigger.dev is open source (Apache-2.0).

Other comparisons with Pushary or Trigger.dev

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.